© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116280
    Prev
    Next
    INDEX
    Explanations

    "-ated" suffixing sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issing
    -0.12
    vip
    -0.12
    ilent
    -0.11
     backstage
    -0.11
    prog
    -0.11
    atinum
    -0.11
    olesterol
    -0.11
     televis
    -0.11
    olest
    -0.11
    allery
    -0.11
    POSITIVE LOGITS
     laden
    0.08
     piv
    0.07
     cush
    0.07
     Mt
    0.07
     slog
    0.07
     Mount
    0.07
     pared
    0.07
     leveraging
    0.07
     receptive
    0.07
     defensive
    0.06
    Activations Density 0.002%

    No Known Activations